ResUNet++ is an advanced architecture for medical image segmentation, specifically designed for colonoscopic polyp detection and segmentation. The paper proposes an improved version of the ResUNet architecture, incorporating residual blocks, squeeze and excitation blocks, Atrous Spatial Pyramidal Pooling (ASPP), and attention blocks. The model is evaluated on two publicly available datasets: Kvasir-SEG and CVC-612. Results show that ResUNet++ significantly outperforms U-Net and ResUNet, achieving a dice coefficient of 81.33% and a mean Intersection over Union (mIoU) of 79.27% on Kvasir-SEG, and a dice coefficient of 79.55% and a mIoU of 79.62% on CVC-612. The model's performance is attributed to its enhanced design, which includes the use of residual units, squeeze and excitation units, ASPP, and attention blocks. The architecture is efficient and effective, even with a smaller number of images. The paper also introduces the Kvasir-SEG dataset, annotated by an expert gastroenterologist, to facilitate research in polyp segmentation. The proposed architecture is suitable for medical image segmentation and can be extended to other pixel-wise classification tasks. The study highlights the importance of using advanced deep learning techniques for accurate and reliable medical image segmentation.ResUNet++ is an advanced architecture for medical image segmentation, specifically designed for colonoscopic polyp detection and segmentation. The paper proposes an improved version of the ResUNet architecture, incorporating residual blocks, squeeze and excitation blocks, Atrous Spatial Pyramidal Pooling (ASPP), and attention blocks. The model is evaluated on two publicly available datasets: Kvasir-SEG and CVC-612. Results show that ResUNet++ significantly outperforms U-Net and ResUNet, achieving a dice coefficient of 81.33% and a mean Intersection over Union (mIoU) of 79.27% on Kvasir-SEG, and a dice coefficient of 79.55% and a mIoU of 79.62% on CVC-612. The model's performance is attributed to its enhanced design, which includes the use of residual units, squeeze and excitation units, ASPP, and attention blocks. The architecture is efficient and effective, even with a smaller number of images. The paper also introduces the Kvasir-SEG dataset, annotated by an expert gastroenterologist, to facilitate research in polyp segmentation. The proposed architecture is suitable for medical image segmentation and can be extended to other pixel-wise classification tasks. The study highlights the importance of using advanced deep learning techniques for accurate and reliable medical image segmentation.